The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
O2C Graph Intelligence — Natural Language SAP Query System
Built a natural language interface over SAP's Order-to-Cash process using an 836-node knowledge graph. Users ask business questions in plain English and get instant answers — no SQL knowledge needed.
What I built:
836-node SAP O2C knowledge graph mapping the full order-to-cash domain
NL→SQL pipeline using Groq + LLaMA 3.3-70B
Live deployed web interface for real-time querying
The hard part:
SAP O2C is a dense enterprise domain — invoicing, collections, order fulfillment, payments. The challenge wasn't just building the LLM pipeline, it was modeling the domain correctly so the queries actually make business sense.
Impact:
Makes complex SAP data accessible to non-technical business users without any SQL or SAP expertise.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Career Compass AI
An AI-powered career navigation platform for students and job seekers in emerging economies.
1. Project Link
2. Short Description
Career Compass AI is an AI-powered career coaching platform designed to help students and early-career professionals navigate their career journey with confidence.
Many learners struggle to understand which skills are valuable, which careers match their strengths, and what steps they should take to become job-ready. Existing solutions often separate learning, career guidance, and job discovery into different platforms.
Career Compass AI brings these experiences together into a single guided journey.
The platform analyzes a user's current skills, recommends suitable career paths, identifies skill gaps, generates personalized learning roadmaps, and tracks career readiness over time.
The core experience follows a simple framework:
Current Skills → Career Goal → Skill Gap Analysis → Learning Roadmap → Job Readiness
The product combines AI coaching, progress tracking, gamification, and data visualization to transform career development into a clear and motivating experience.
3. Key Features
AI Career Assessment
Skill discovery and assessment
Career recommendations
Match percentage scoring
Career Readiness Dashboard
Readiness score
Skill progress tracking
Career milestones
Skill Gap Analysis
Missing skills identification
Progress visualization
Personalized recommendations
Learning Roadmap
Step-by-step growth plan
Learning milestones
Progress tracking
AI Career Coach
Career guidance
Learning recommendations
Interview preparation assistance
Gamification
Achievement badges
Learning streaks
Career progression levels
4. Screenshots
Include:
Screenshot 1 — Dashboard
Caption:
The main dashboard provides an overview of career readiness, skill progress, learning milestones, and AI coaching recommendations.
Screenshot 2 — Skill Gap Analysis
Caption:
Users can compare their current skills against career requirements and identify areas for improvement.
Screenshot 3 — Learning Roadmap
Caption:
Personalized roadmaps guide users through the most effective path toward their target career.
Screenshot 4 — AI Coach
Caption:
The AI Career Coach provides personalized guidance, career insights, and actionable next steps.
5. How I Used Stitch
Stitch was used as the primary interface generation tool for rapidly designing and iterating on product screens.
The workflow included:
Defining the product concept and user journey.
Creating a design system and brand direction.
Using Stitch to generate initial dashboard and workflow screens.
Refining layouts through iterative prompting.
Improving alignment, spacing, visual hierarchy, and branding consistency.
Establishing a consistent component library including cards, navigation patterns, progress indicators, and AI coaching elements.
Using Stitch to expand the design language across multiple screens while maintaining a unified visual identity.
The platform significantly accelerated exploration and iteration, allowing rapid testing of different layouts and user experiences before moving into detailed refinement.
Advanced Workflow
To improve consistency and quality, I used Stitch's design import capability rather than starting from a blank prompt.
The imported Figma file served as the source of truth for:
Branding
Design tokens
Component styling
Typography
Layout patterns
This enabled a scalable workflow where AI-generated screens inherited the established design language instead of creating entirely new visual directions.
By combining manual design system creation with AI-assisted generation, I was able to move from a single dashboard concept to a cohesive multi-screen product experience much faster than a traditional workflow.
6. Design Decisions
The product was intentionally designed as a "career navigation system" rather than a traditional job board.
Key design principles included:
Clarity over complexity
Progress-focused interactions
Visual motivation through gamification
Strong information hierarchy
Career journey storytelling
The visual language emphasizes growth, momentum, and achievement through roadmaps, progress indicators, readiness scores, and milestone-based experiences.
The brand combines the motivational qualities of learning platforms with the clarity and polish of modern SaaS products.
7. Feedback on Stitch
What Worked Well
Fast screen generation
Rapid concept exploration
Helpful for dashboard layouts
Effective starting point for complex interfaces
Accelerated product thinking and iteration
Challenges
Design consistency sometimes varied across generated screens
Alignment and spacing occasionally required manual refinement
Branding needed explicit design system guidance
Visual hierarchy improved significantly when detailed design prompts were provided
Suggestions
Stronger support for reusable design systems
Improved consistency across generated screens
Better preservation of established branding across iterations
Enhanced component-level control
8. Bonus: Workflow Walkthrough
Workflow Summary
Defined product problem.
Created user journey.
Designed brand identity.
Built dashboard concept.
Generated screens using Stitch.
Refined layouts and branding.
Created final prototype.
Bonus: Advanced Elements Used
Interactive Behaviors
Career readiness tracking
Progress-based dashboards
Learning roadmap interactions
Dynamic AI coaching interface
Design System
Custom color palette
Typography scale
Reusable card components
Progress visualization framework
AI Features
Career matching
Skill gap analysis
Personalized learning recommendations
Career coaching assistant
Submission Summary
Project: Career Compass AI
Category: AI + Education + Career Development
Problem Solved:
Helping students and job seekers understand where they are, where they want to go, and how to get there.
Core Value Proposition:
"Tell us your skills today, and we'll show you the fastest path to your future career."
Love the idea of treating career growth like navigation rather than job searching. The "Current Skills → Career Goal → Skill Gap → Roadmap → Readiness" journey makes the experience feel much more actionable for students and early-career professionals. Great use of Stitch to turn a complex problem into a clear visual workflow. 👏
With the help of Stitch I've invented Outreach OS : A LinkedIn outreach command center for B2B Sales Teams & Reps.
The problem: Sales Teams use sometime more than 6 tools to run a single outreach campaign.
The solution & Features:
• Kanban pipeline with urgency indicators
• Message composer with tone-switching
• HOT / WARM / COLD reply classifier
• Lead detail panel with message history
Every interaction built with in-place AI prompts. No code. No Figma. Just Stitch.
Built entirely in Google Stitch across a 24-hour sprint. Started with 4 hand-drawn sketches, imported them using Stitch's image-to-UI feature (Experimental Mode), then watched streaming generation turn rough wireframes into a polished interface.
Prototype link: https://stitch.withgoogle.com/preview/8588058872149547690?node-id=e612ae5bfdce41a3a725aaf230968d39
I used in-place AI edits for every interaction refinement; hover states, card elevation, the sliding detail panel, the animated tone-switcher pill.
One anchor prompt and a bit of iteration and I was able to end up with a product that looks like it was built over weeks.
Had a lot of fun creating this one, Stitch is changing the Software Development Cycle in real time!
Wow, Olayinka, this is an incredibly powerful and practical tool! Turning a chaotic, multi-tool workflow into a single LinkedIn outreach command center is a brilliant concept.
Fantastic execution! I also just submitted my project for the challenge, STALL, a Swipe-to-Shop App...
on.contra.com
Swipe-to-Shop App Transforming Farmers Market Experience
Connect with next-gen talent and tools to get work underway. Hire more independents. Start more projects. Get more creative.
Challenges
View all
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
MagicPath
The canvas is infinite, and exploration is becoming the workflow. How are you using MagicPath?
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?
